CN104700085A - Template matching-based chip positioning method - Google Patents
Template matching-based chip positioning method Download PDFInfo
- Publication number
- CN104700085A CN104700085A CN201510104012.3A CN201510104012A CN104700085A CN 104700085 A CN104700085 A CN 104700085A CN 201510104012 A CN201510104012 A CN 201510104012A CN 104700085 A CN104700085 A CN 104700085A
- Authority
- CN
- China
- Prior art keywords
- chip
- template
- image block
- pixel
- bianry image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a template matching-based chip positioning method. The method specifically comprises the following steps: I, manufacturing a template; II, preprocessing a to-be-positioned image to increase contrast of background and a chip substrate; III, performing image segmentation on the preprocessed image to obtain blocks, and eliminating chips with crystal stock and missing defects by using the areas of the blocks and the side information on a minimum boundary rectangle corresponding to the blocks; acquiring a central position coordinate of the minimum boundary rectangle of the remaining blocks and an included angle of a short side and the horizontal direction; IV, positioning the position and the angle of the chip by using a template matching chip on the to-be-positioned image according to the central position coordinate and the included angle obtained by the step III. The method is mainly suitable for positioning the chip in the chip manufacturing process, the position of a qualified chip can be quickly and accurately determined by using a screening and matching method, and the chips with the crystal stock and missing defects are eliminated.
Description
Technical field
The invention belongs to technical field of image processing, more specifically, relate to a kind of chip positioning method based on template matches.
Background technology
In chip manufacturing proces, cause the chip containing band crystal stock, defect flaw in the chip of output owing to cutting bad, affect chip quality, need to position chip, find out qualified chip, get rid of the chip of band crystal stock, defect flaw.In prior art, the general method of universality template matches that adopts carrys out positioning chip, and the universality matching process had at present is divided three classes: the matching process based on gray-scale value, the matching algorithm based on geometric properties and the matching process based on gradient direction; Wherein based on the matching process of gray-scale value when soft edge, also can match target to degree of precision, but the method to the stability of light source and uniformity requirement very high; Based on the matching algorithm of geometric properties, comprise based on geometric primitive and the method comprising feature based angle point, high to image quality requirements, be easily subject to noise; Direct utilization carrys out positioning chip owing to having certain fault-tolerant ability based on the matching algorithm of gradient direction, defect can be mistakened as and be made noise, accurately can not get rid of the defective chip of band crystal stock or defect.
Above-described method is all the method for universality, at present also not for the template matching method of chip positioning, the template matching method of universality does not consider the feature of chip and the requirement of chip manufacturing process, the defective chip of band crystal stock or defect can not be excluded.
Summary of the invention
For above defect or the Improvement requirement of prior art, the invention provides a kind of chip positioning method based on template matches, its object is to find out region corresponding to qualified chip by the bianry image block (blob block) on template Stepwise Screening picture to be positioned, then mate with template parameter in this region, orient position and the angle of qualified chip; This method energy quick position mated afterwards that first screens goes out qualified chip.
For achieving the above object, according to one aspect of the present invention, provide a kind of chip positioning method based on template matches, comprise and make matching template process and template matches position fixing process, specific as follows:
(1) gather picture to be positioned and obtain original template according to picture; Rotate original template with default step-length, often rotate and once obtain a matching template; Rotate repeatedly until traversal original template and the differential seat angle intended between the chip that mates in the horizontal direction; Wherein original template refers to that of choosing on picture to be positioned revolves the picture of flat qualified chip; In the present invention, mainly judge that whether chip is qualified from the angle of cutting technique; Select clear-cut, internal electrode edge clear and the picture of the sharp-edged qualified chip of electrode gold thread as original template;
(2) area of original template, length of side parameter, the gradient direction of pixel and Grad and template matches feature is obtained; And extract gradient direction and the Grad of all matching templates, complete template construct; Wherein template matches feature refers to that on each matching template, its Grad exceedes the gradient direction of the pixel of predetermined threshold value; When template matches feature extraction, choose as much as possible concentrate on edge and chip light emitting district that chip basal body and background interface edge, chip light emitting district and chip electrode have a common boundary and the edge that gold thread has a common boundary pixel on extract gradient direction;
(3) pre-service is carried out to increase the contrast between chip basal body and background to picture to be positioned; Adopt gray level threshold segmentation method to carry out Iamge Segmentation to pretreated picture, obtain bianry image block;
(4) in bianry image block, filter out the bianry image block area matched with original template with original template area for benchmark, be referred to as the first bianry image block;
(5) in the first bianry image block, filter out for benchmark the bianry image block that its minimum enclosed rectangle length of side mates with the original template length of side with the original template length of side, be referred to as the second bianry image block; The region that described second bianry image block is corresponding on picture to be positioned is target area;
(6) in described target area, region corresponding to qualified chip is matched according to the minimum enclosed rectangle central point of the second bianry image block and minimum enclosed rectangle minor face with the angle of horizontal direction; Within positive and negative 5 pixels of the second bianry image block minimum enclosed rectangle center position and the scope of the angle of the minor face of minimum enclosed rectangle and horizontal direction within positive and negative 5 degree and region corresponding to qualified chip;
(7) remove in the region that described qualified chip is corresponding the gradient direction mating corresponding pixel points by template matches feature, travel through described region, until find out the coordinate of point and the anglec of rotation of template that and correlation degree value maximum with template degree of correlation be greater than 0.75, be the coordinate of qualified chip central point and the angle of qualified chip, orient qualified chip thus.
Preferably, in step (1), the step-length preset is chosen within the scope of 0 to 1 degree, determines according to accuracy requirement, selects suitable step-length to reduce match complexity while guarantee precision.
Preferably, the preprocessing process in step (3) is specially: according to formula (1) with the original value of the mean value of pixel for benchmark adjustment pixel, obtain pixel enhancement value to increase the contrast between chip basal body and background;
Wherein, i, j represent the transverse and longitudinal coordinate of pixel (i, j) on picture to be positioned respectively; R (i, j) represents the pixel original value of point (i, j);
represent to preset centered by point (i, j) in side size range the mean value of pixel a little; C is for strengthening coefficient; S (i, j) represents the pixel enhancement value of point (i, j) after treatment.
Preferably, the side size range preset in preprocessing process is 20 to 40 pixels, with in this pixel coverage the mean value of pixel a little go balanced original pixels can increase contrast between chip basal body and background to the full extent.
Preferably, in preprocessing process, strengthen coefficient C value between 0 to 10, determine according to light-source brightness and chip kind.
Preferably, step (4) is specially: compare bianry image block area and original template area, retains its area and is greater than the bianry image block that template area 85% is less than template area 115%, i.e. the first bianry image block; Within the area of the first bianry image block being limited to positive and negative 15% scope of template area, farthest can filter out qualified chip, avoid erroneous judgement.
Preferably, step (5) is specially: in the first bianry image block, filter out the bianry image block of its minimum enclosed rectangle length of side in the length of side 90% ~ 110% scope that original template is corresponding with the original template length of side for benchmark, be the second bianry image block; The boundary rectangle length of side of the second bianry image block is limited in positive and negative 10% scope of the corresponding length of side of template, further reduces screening scope, improve positioning precision, also reduce the complexity of gradient coupling simultaneously.
Preferably, in step (7), the minor face being chosen at minimum enclosed rectangle is done with the template matches feature of the template within the scope of positive and negative 5 degree of the angle of horizontal direction and is mated, and orients qualified chip.
Preferably, in step (2), the predetermined threshold value of described Grad is 0 to 40, this scope get Grad can by intend choosing the intersection of the whole limited chip matrix of pixel of gradient direction and background, chip electrode and luminous zone edge on or electrode gold thread and luminous zone edge on, strengthen the discrimination of chip basal body and background, avoid noise.
In general, the above technical scheme conceived by the present invention compared with prior art, can obtain following beneficial effect:
(1) owing to only have chosen the gradient direction of unique point as matching characteristic when making template, therefore there is good adaptability to the change of noise and illumination condition, make chip positioning method provided by the invention have very high antijamming capability and robustness is good;
(2) owing to present invention employs pretreated step, this feature of larger contrast is there is according to chip basal body and background, orient the potential site of qualified chip, and the chip excluded containing crystal stock, defect flaw, greatly reduce the region of intending coupling, improve chip positioning efficiency, reduce the complexity of chip positioning;
(3) owing to present invention employs first with template parameter screening, then go the method for mating by template matches feature, reduce the region of template matches greatly, improve chip positioning efficiency; On the other hand, the prior art of positioning chip is carried out compared to directly using the matching algorithm based on gradient direction, owing to there being preposition postsearch screening process before matching, greatly reducing and defect is mistakened as the erroneous judgement possibility being made noise and causing, improve positional accuracy.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the inventive method;
Fig. 2 is the original LED chip picture in embodiment 1;
Fig. 3 is the template picture chosen in embodiment 1;
Fig. 4 be in embodiment 1 original LED chip picture through pretreated picture;
Fig. 5 carries out the result figure after gray level threshold segmentation to Fig. 4 in embodiment 1;
Fig. 6 is blob block remaining after screening to the blob block obtained after Fig. 5 segmentation in embodiment 1;
Fig. 7 is the region that the blob block in embodiment 1 after screening is corresponding on original graph LED chip picture;
Fig. 8 is the result of template matches;
In all of the figs, identical Reference numeral is used for representing identical element or structure, and wherein: 1-exists the chip of defect flaw, 2-exists the chip of crystal stock defect.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.In addition, if below in described each embodiment of the present invention involved technical characteristic do not form conflict each other and just can mutually combine.
Be illustrated in figure 1 the process flow diagram of chip positioning method provided by the invention, specifically comprise template construct and template matches locates two key steps; Wherein, chip positioning step comprises following sub-step: the pre-service of image is to improve the contrast of chip basal body and background; Iamge Segmentation and blob block analysis, filter out the region that may there is qualified chip and the possible angle of chip; Template matches location is carried out to the blob block of the reservation after screening.
Figure 2 shows that original LED chip picture in embodiment 1, below for embodiment 1, the specific implementation process of chip positioning method provided by the invention be described:
(1) original LED chip picture to be positioned is gathered, as shown in Figure 2; Original LED chip picture to be positioned is selected clear-cut, internal electrode edge clear and gold thread is sharp-edged revolves flat qualified chip as original template, is the template picture chosen in embodiment 1 as shown in Figure 3; Obtain the area A of template
twith the length of side of template, wherein, l
tfor length of long sides, w
tlength of short sides, each parameter value is as shown in table 1 below:
Table 1 original template parameter list
| Template parameter | Parameter value |
| Area A T | 4347 pixels |
| Length of long sides l T | 69 pixels |
| Length of short sides w T | 63 pixels |
(2) gradient direction and the Grad of original template image pixel is obtained, choose corresponding Grad and exceed the gradient direction of predetermined threshold value as template matches feature, make template matches feature concentrate on the edge of chip basal body and background, the method obtaining the Grad G of original template image pixel and gradient direction θ (-π < θ≤π) is specific as follows:
Adopt G
xrepresent this pixel Grad in the horizontal direction, adopt G
yrepresent the Grad of this pixel at vertical direction; Grad
gradient direction angle θ value specific as follows:
If G
x> 0, then
If G
x< 0 and G
y< 0, then
If G
x< 0 and G
y> 0, then
If G
x=0 and G
y> 0, then
If G
x=0 and G
y< 0, then
If G < is Constant, then show that this point is not unique point;
Wherein, Constant is the threshold value of Grad, in embodiment 1, preset Constant=20;
(3) more template is made by rotating original template: in 30 degree of chip angle of intending coupling, with 0.2 degree for rotary step, often rotate 0.2 degree of making template, until traversal 30 degree; Extract gradient direction and the Grad of all templates according to the method for above step (2), complete template construct; In each template, choose Grad be greater than the gradient direction feature of the pixel of Constant as template matches feature;
(4) pre-service is carried out to the original LED chip picture to be positioned shown in Fig. 2, is specially: according to formula (1), with the original value of the mean value of pixel for benchmark adjustment pixel, obtain pixel enhancement value,
Wherein, i, j represent the transverse and longitudinal coordinate of pixel (i, j) on picture to be positioned respectively; R (i, j) represents the pixel original value of point (i, j);
represent that template size is the mean value of the pixel of 30 × 30; C, for strengthening coefficient, is taken as 5 in embodiment 1; S (i, j) represents point (i, j) pixel enhancement value after treatment; Especially, if certain pixel value r (i, j) >=200, in pre-service r in season (i, j)=200, so that whole pixel value is controlled in OK range;
Figure 4 shows that Fig. 2 is through pretreated image, found with Fig. 2 by comparison diagram 4, on pretreated picture, chip basal body brightens, and background is dimmed, and the contrast of pretreated picture chips matrix and background is improved significantly;
(5) Iamge Segmentation and blob analyze: adopt gray level threshold segmentation method, utilize chip basal body and the background difference in gray scale, choosing gray threshold is 70, by the pixel gray scale in Fig. 4 and gray threshold being compared, carries out Iamge Segmentation to Fig. 4; Then through opening operation and area filling, obtain multiple blob block, after segmentation, result as shown in Figure 5, and on Fig. 5, white color lump is the blob block split; Composition graphs 2 and Fig. 5 comparative analysis find, the region that blob block covers is nearly all containing LED chip;
(6) area A of each blob block in Fig. 5 is obtained
i, with the area A of template
tfor benchmark carries out preliminary screening, exclude A
ibe less than 0.85*A
tor area is greater than 1.15*A
tblob block;
(7) the blob block retained after step (6) screening is screened further: the length of side of the minimum enclosed rectangle that each blob block that acquisition retains is corresponding, wherein long limit is l
i, minor face is w
i; Center pixel coordinate (the x of corresponding minimum enclosed rectangle
i, y
j), the angle α of minor face and horizontal direction
i, according to length of side constraint condition exclusive segment blob block, concrete: by l
i< 90%l
tor w
i< 90%w
tor l
i> 110%l
tor w
i> 110%w
tblob block get rid of, wherein, l
tand w
tfor the length of side of template; The blob block screened as shown in Figure 6;
(8) region of remaining after step (7) screening blob block correspondence on original chip picture to be positioned is the potential distributed areas of qualified chip; The center of chip is with (x
i, y
j) be the center of circle, radius is in the region of 5 pixels, and the coupling angle of chip is at α
ipositive and negative 5 degree within;
Table 2 is blob block position coordinates (x in Fig. 6
i, y
i) and minor face and horizontal direction angle (being just counterclockwise) α
i; Sortord falls down from above according to blob each in Fig. 6, order serialization number from left to right:
The position of Blob block and angle parameter in table 2 Fig. 6
| Sequence number | Row x i | Column y i | Angle [alpha] i(degree) |
| 1 | 69 | 89 | 0 |
| 2 | 71.49 | 360.49 | 1.1 |
| 3 | 72.41 | 451.42 | 0.88 |
| 4 | 72.01 | 542.48 | 0.91 |
| 5 | 165.61 | 87.50 | 0.99 |
| 6 | 167.5 | 359 | 0 |
| 7 | 168 | 450 | 0 |
| 8 | 168.09 | 541.41 | 0.94 |
| 9 | 262 | 86 | 0 |
| 10 | 264.44 | 357.33 | 1.27 |
| 11 | 264.47 | 448.49 | 0.94 |
| 12 | 263.92 | 539.54 | 1.01 |
| 13 | 358.88 | 85.47 | 1.22 |
| 14 | 359.5 | 357 | 0 |
| 15 | 359.5 | 447 | 0 |
| 16 | 359.48 | 538.28 | 0.97 |
(9) the coupling location of chip: the region that on the original chip picture that step (8) obtains, qualified chip is corresponding, as shown in gray area on Fig. 7;
In the region shown in Fig. 7, go the gradient direction mating corresponding point in described region to mate one by one by 150 templates by template matches feature, travel through described region, until find out the coordinate of point and the anglec of rotation of template that and correlation degree value maximum with template degree of correlation be greater than 0.75; Be qualified chip center point coordinate (xsubp
i, ysubp
i) and angle θ subp
i; Matching result as shown in Figure 8, on original chip image, is identified by the chip white box matched, and the central point of the white crosses sensing at white box center is the central point of qualified chip.
As can be seen from Figure 8, what match is qualified chip, and the chip containing crystal stock, defect flaw is all excluded.By the position of chip that matches and angle parameter in table 3 corresponding diagram 8, in corresponding diagram 8, each chip is according to from left to right, order serialization number from top to bottom:
Table 3 is by the position of qualified chip that matches and angle parameter
| Sequence number | Row xsubp i | Column ysubp i | Angle θ subp i(degree) |
| 1 | 69.70 | 89.84 | 0.038 |
| 2 | 72.14 | 360.90 | 0.036 |
| 3 | 72.07 | 452 | 0.46 |
| 4 | 72.77 | 542.96 | 0.19 |
| 5 | 165.83 | 88.06 | 0.18 |
| 6 | 168.73 | 359.67 | 0.35 |
| 7 | 168.68 | 451.52 | 0.59 |
| 8 | 168.77 | 541.71 | -0.33 |
| 9 | 262.09 | 86.77 | 1.04 |
| 10 | 263.96 | 358.18 | 0.06 |
| 11 | 264 | 459 | 0 |
| 12 | 264.10 | 541.03 | 0.24 |
| 13 | 358.38 | 85.95 | -1.32 |
| 14 | 359.82 | 357.27 | 0.49 |
| 15 | 360.60 | 448.08 | 0.71 |
| 16 | 359.98 | 539.09 | 0.25 |
The chip positioning method provided by embodiments of the invention 1, is adopted template first to screen the mode of mating again, can get rid of defective chip fast, orient qualified chip.
Those skilled in the art will readily understand; the foregoing is only preferred embodiment of the present invention; not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (9)
1. based on a chip positioning method for template matches, it is characterized in that, described chip positioning method is specific as follows:
(1) gather picture to be positioned and obtain original template according to picture; Rotate original template with default step-length, often rotate and once obtain a matching template; Rotate repeatedly until traversal original template and the differential seat angle intended between the chip that mates in the horizontal direction; Wherein original template refers to and choose the picture that revolves flat qualified chip on picture to be positioned;
(2) area of original template, length of side parameter, the gradient direction of pixel and Grad and template matches feature is obtained; And extract gradient direction and the Grad of all matching templates, complete template construct; Wherein template matches feature refers to that on each matching template, its Grad exceedes the gradient direction of the pixel of predetermined threshold value;
(3) pre-service is carried out to increase the contrast between chip basal body and background to picture to be positioned; Adopt gray level threshold segmentation method to carry out Iamge Segmentation to pretreated picture, obtain bianry image block;
(4) with original template area for benchmark filters out the first bianry image block area matched with original template in bianry image block;
(5) with the original template length of side for benchmark filters out the second bianry image block that its minimum enclosed rectangle length of side mates with the original template length of side in the first bianry image block; The region that described second bianry image block is corresponding on picture to be positioned is target area;
(6) in described target area, region corresponding to qualified chip is matched according to the minimum enclosed rectangle central point of the second bianry image block and minimum enclosed rectangle minor face with the angle of horizontal direction; Within positive and negative 5 pixels of the second bianry image block minimum enclosed rectangle center position and the scope of the angle of the minor face of minimum enclosed rectangle and horizontal direction within positive and negative 5 degree and region corresponding to qualified chip;
(7) remove in the region that described qualified chip is corresponding the gradient direction mating corresponding pixel points by template matches feature, travel through described region, until find out the coordinate of point and the anglec of rotation of template that and correlation degree value maximum with template degree of correlation be greater than 0.75, be the coordinate of qualified chip central point and the angle of qualified chip, orient qualified chip thus.
2. chip positioning method as claimed in claim 1, is characterized in that, in step (1), the step-length preset is chosen within the scope of 0 to 1 degree, determines according to accuracy requirement.
3. chip positioning method as claimed in claim 1, it is characterized in that, preprocessing process in described step (3) is specially: according to formula (1) with the original value of the mean value of pixel for benchmark adjustment pixel, obtain pixel enhancement value to increase the contrast between chip basal body and background;
Wherein, i, j represent the transverse and longitudinal coordinate of pixel (i, j) on picture to be positioned respectively; R (i, j) represents the pixel original value of point (i, j);
represent to preset centered by point (i, j) in side size range the mean value of pixel a little; C is for strengthening coefficient; S (i, j) represents the pixel enhancement value of point (i, j) after treatment.
4. chip positioning method as claimed in claim 3, it is characterized in that, described default side size range is 20 to 40 pixels.
5. the chip positioning method as described in claim 3 or 4, is characterized in that, in preprocessing process, strengthens coefficient C value between 0 to 10.
6. chip positioning method as claimed in claim 1, it is characterized in that, step (4) is specially: bianry image block area and original template area are compared, and retains its area and is greater than the bianry image block that template area 85% is less than template area 115%.
7. chip positioning method as claimed in claim 1, it is characterized in that, step (5) is specially: with the original template length of side for benchmark filters out the bianry image block of its minimum enclosed rectangle length of side in the length of side 90% ~ 110% scope that original template is corresponding in the first bianry image block.
8. chip positioning method as claimed in claim 1, it is characterized in that, in step (7), the minor face being chosen at minimum enclosed rectangle is done with the template matches feature of the template within the scope of positive and negative 5 degree of the angle of horizontal direction and is mated, and orients qualified chip.
9. chip positioning method as claimed in claim 1, it is characterized in that, in step (2), the predetermined threshold value of described Grad is 0 to 40.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510104012.3A CN104700085B (en) | 2015-03-10 | 2015-03-10 | A kind of chip positioning method based on template matches |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510104012.3A CN104700085B (en) | 2015-03-10 | 2015-03-10 | A kind of chip positioning method based on template matches |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104700085A true CN104700085A (en) | 2015-06-10 |
| CN104700085B CN104700085B (en) | 2018-02-27 |
Family
ID=53347184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510104012.3A Active CN104700085B (en) | 2015-03-10 | 2015-03-10 | A kind of chip positioning method based on template matches |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104700085B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
| CN106780437A (en) * | 2016-11-11 | 2017-05-31 | 东南大学 | A kind of quick QFN chips plastic packaging image is obtained and amplification method |
| CN108335296A (en) * | 2018-02-28 | 2018-07-27 | 中际山河科技有限责任公司 | A kind of pole plate identification device and method |
| CN112085033A (en) * | 2020-08-19 | 2020-12-15 | 浙江华睿科技有限公司 | Template matching method and device, electronic equipment and storage medium |
| CN112150541A (en) * | 2020-09-10 | 2020-12-29 | 中国石油大学(华东) | Multi-LED wafer positioning algorithm |
| CN112184715A (en) * | 2020-11-10 | 2021-01-05 | 武汉工程大学 | Method for calculating theoretical center of welding spot of BGA image |
| CN112216640A (en) * | 2020-10-19 | 2021-01-12 | 惠州高视科技有限公司 | Semiconductor chip positioning method and device |
| CN112419224A (en) * | 2020-07-17 | 2021-02-26 | 宁波智能装备研究院有限公司 | Spherical pin chip positioning method and system |
| WO2021134996A1 (en) * | 2019-12-30 | 2021-07-08 | 研祥智能科技股份有限公司 | Defect determining method and system for led support |
| CN113269743A (en) * | 2021-05-20 | 2021-08-17 | 北京理工大学重庆创新中心 | Chip quantity detection method based on iterative translation verification |
| CN113305017A (en) * | 2021-05-28 | 2021-08-27 | 柳州源创电喷技术有限公司 | Comprehensive intelligent detection and sorting method for full-automatic valve element |
| CN114187294A (en) * | 2022-02-16 | 2022-03-15 | 常州铭赛机器人科技股份有限公司 | Regular wafer positioning method based on prior information |
| CN115062350A (en) * | 2022-06-10 | 2022-09-16 | 深圳市一卓科技有限公司 | Correlation matching system of Internet of things and security chip |
| CN115375679A (en) * | 2022-10-24 | 2022-11-22 | 广东工业大学 | Edge finding and point searching positioning method and device for defective chip |
| CN115423814A (en) * | 2022-11-07 | 2022-12-02 | 江西兆驰半导体有限公司 | Chip origin positioning method and device, readable storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6175417B1 (en) * | 1998-02-13 | 2001-01-16 | Micron Technology, Inc. | Method and apparatus for detecting defects in the manufacture of an electronic device |
| US20100202706A1 (en) * | 2009-02-12 | 2010-08-12 | Maria Gabrani | Ic layout pattern matching and classification system and method |
| CN102938077A (en) * | 2012-10-25 | 2013-02-20 | 渭南师范学院 | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation |
| CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
-
2015
- 2015-03-10 CN CN201510104012.3A patent/CN104700085B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6175417B1 (en) * | 1998-02-13 | 2001-01-16 | Micron Technology, Inc. | Method and apparatus for detecting defects in the manufacture of an electronic device |
| US20100202706A1 (en) * | 2009-02-12 | 2010-08-12 | Maria Gabrani | Ic layout pattern matching and classification system and method |
| CN102938077A (en) * | 2012-10-25 | 2013-02-20 | 渭南师范学院 | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation |
| CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
Non-Patent Citations (2)
| Title |
|---|
| 朱铮涛 等: "基于特征点的形状匹配技术及其算法实现", 《计算机工程与设计》 * |
| 王平 等: "基于改进模板匹配的芯片缺陷检测方法", 《微计算机信息（测控自动化）》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046271B (en) * | 2015-06-25 | 2018-03-30 | 哈尔滨工业大学 | The positioning of MELF elements and detection method based on template matches |
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
| CN106780437A (en) * | 2016-11-11 | 2017-05-31 | 东南大学 | A kind of quick QFN chips plastic packaging image is obtained and amplification method |
| CN106780437B (en) * | 2016-11-11 | 2019-10-11 | 东南大学 | A kind of quick QFN chip plastic packaging image obtains and amplification method |
| CN108335296A (en) * | 2018-02-28 | 2018-07-27 | 中际山河科技有限责任公司 | A kind of pole plate identification device and method |
| CN108335296B (en) * | 2018-02-28 | 2021-10-01 | 中际山河科技有限责任公司 | Polar plate identification device and method |
| WO2021134996A1 (en) * | 2019-12-30 | 2021-07-08 | 研祥智能科技股份有限公司 | Defect determining method and system for led support |
| CN112419224A (en) * | 2020-07-17 | 2021-02-26 | 宁波智能装备研究院有限公司 | Spherical pin chip positioning method and system |
| CN112419224B (en) * | 2020-07-17 | 2021-08-27 | 宁波智能装备研究院有限公司 | Spherical pin chip positioning method and system |
| CN112085033A (en) * | 2020-08-19 | 2020-12-15 | 浙江华睿科技有限公司 | Template matching method and device, electronic equipment and storage medium |
| CN112085033B (en) * | 2020-08-19 | 2024-04-09 | 浙江华睿科技股份有限公司 | Template matching method and device, electronic equipment and storage medium |
| CN112150541A (en) * | 2020-09-10 | 2020-12-29 | 中国石油大学(华东) | Multi-LED wafer positioning algorithm |
| CN112216640A (en) * | 2020-10-19 | 2021-01-12 | 惠州高视科技有限公司 | Semiconductor chip positioning method and device |
| CN112184715B (en) * | 2020-11-10 | 2022-07-19 | 武汉工程大学 | Method for calculating welding spot theoretical center of BGA image |
| CN112184715A (en) * | 2020-11-10 | 2021-01-05 | 武汉工程大学 | Method for calculating theoretical center of welding spot of BGA image |
| CN113269743A (en) * | 2021-05-20 | 2021-08-17 | 北京理工大学重庆创新中心 | Chip quantity detection method based on iterative translation verification |
| CN113305017A (en) * | 2021-05-28 | 2021-08-27 | 柳州源创电喷技术有限公司 | Comprehensive intelligent detection and sorting method for full-automatic valve element |
| CN113305017B (en) * | 2021-05-28 | 2022-11-08 | 柳州源创电喷技术有限公司 | Comprehensive intelligent detection and sorting method for full-automatic valve element |
| CN114187294A (en) * | 2022-02-16 | 2022-03-15 | 常州铭赛机器人科技股份有限公司 | Regular wafer positioning method based on prior information |
| CN115062350A (en) * | 2022-06-10 | 2022-09-16 | 深圳市一卓科技有限公司 | Correlation matching system of Internet of things and security chip |
| CN115062350B (en) * | 2022-06-10 | 2023-11-24 | 深圳市一卓科技有限公司 | Correlation matching system of Internet of things and security chip |
| CN115375679A (en) * | 2022-10-24 | 2022-11-22 | 广东工业大学 | Edge finding and point searching positioning method and device for defective chip |
| CN115423814A (en) * | 2022-11-07 | 2022-12-02 | 江西兆驰半导体有限公司 | Chip origin positioning method and device, readable storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104700085B (en) | 2018-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104700085A (en) | Template matching-based chip positioning method | |
| CN114723701B (en) | Gear defect detection method and system based on computer vision | |
| DE102020100684B4 (en) | MARKING OF GRAPHICAL REFERENCE MARKERS | |
| US11915407B2 (en) | Automated system and method for clarity measurements and clarity grading | |
| CN108876743B (en) | Image rapid defogging method, system, terminal and storage medium | |
| CN109215026B (en) | High-speed accurate LED defect detection method based on machine vision | |
| CN114821114B (en) | Groove cutting robot image processing method based on vision system | |
| CN103761534B (en) | A kind of detection method for QFP element vision localization | |
| CN110286126A (en) | A kind of wafer surface defects subregion area detecting method of view-based access control model image | |
| CN109636772A (en) | The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning | |
| TWI497450B (en) | Visual object tracking method | |
| CN106897994A (en) | A kind of pcb board defect detecting system and method based on layered image | |
| CN107315012B (en) | Composite polycrystal-diamond end face collapses the intelligent detecting method at angle | |
| CN104677914A (en) | Method for identifying crystal stock defect of chip | |
| WO2020038312A1 (en) | Multi-channel tongue body edge detection device and method, and storage medium | |
| CN109767431A (en) | Accessory appearance defect inspection method, device, equipment and readable storage medium storing program for executing | |
| CN102881017A (en) | Cell separation method | |
| CN115866502A (en) | Microphone part surface defect online detection process | |
| CN112784894B (en) | Automatic labeling method for rock slice microscopic image | |
| Gao et al. | Intelligent crack damage detection system in shield tunnel using combination of retinanet and optimal adaptive selection | |
| CN111986802A (en) | Auxiliary judgment system and method for lung adenocarcinoma pathological differentiation grade | |
| CN107578414A (en) | A kind of processing method of pavement crack image | |
| Meng et al. | Defect detection of glassivation passivation parts wafer surface with random texture and different brightness | |
| CN111640122A (en) | Light spot positioning and dividing method for LED (light emitting diode) special-shaped display screen based on connected domain | |
| CN111612738A (en) | Chrysanthemum pattern geometric information extraction method based on detection of straight lines and line segments |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |